yt_dlp/extractor/washingtonpost.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import traverse_obj
   5
   6
   7 class WashingtonPostIE(InfoExtractor):
   8     IE_NAME = 'washingtonpost'
   9     _VALID_URL = r'(?:washingtonpost:|https?://(?:www\.)?washingtonpost\.com/(?:video|posttv)/(?:[^/]+/)*)(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
  10     _EMBED_REGEX = [r'<iframe[^>]+\bsrc=["\'](?P<url>https?://(?:www\.)?washingtonpost\.com/video/c/embed/[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})']
  11     _TESTS = [{
  12         'url': 'https://www.washingtonpost.com/video/c/video/480ba4ee-1ec7-11e6-82c2-a7dcb313287d',
  13         'md5': '6f537e1334b714eb15f9563bd4b9cdfa',
  14         'info_dict': {
  15             'id': '480ba4ee-1ec7-11e6-82c2-a7dcb313287d',
  16             'ext': 'mp4',
  17             'title': 'Egypt finds belongings, debris from plane crash',
  18             'description': 'md5:a17ceee432f215a5371388c1f680bd86',
  19             'upload_date': '20160520',
  20             'timestamp': 1463775187,
  21         },
  22     }, {
  23         'url': 'https://www.washingtonpost.com/video/world/egypt-finds-belongings-debris-from-plane-crash/2016/05/20/480ba4ee-1ec7-11e6-82c2-a7dcb313287d_video.html',
  24         'only_matching': True,
  25     }, {
  26         'url': 'https://www.washingtonpost.com/posttv/world/iraq-to-track-down-antiquities-after-islamic-state-museum-rampage/2015/02/28/7c57e916-bf86-11e4-9dfb-03366e719af8_video.html',
  27         'only_matching': True,
  28     }]
  29
  30     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  32         return self.url_result(
  33             'arcpublishing:wapo:' + video_id, 'ArcPublishing', video_id)
  34
  35
  36 class WashingtonPostArticleIE(InfoExtractor):
  37     IE_NAME = 'washingtonpost:article'
  38     _VALID_URL = r'https?://(?:www\.)?washingtonpost\.com/(?:[^/]+/)*(?P<id>[^/?#]+)'
  39     _TESTS = [{
  40         'url': 'http://www.washingtonpost.com/sf/national/2014/03/22/sinkhole-of-bureaucracy/',
  41         'info_dict': {
  42             'id': 'sinkhole-of-bureaucracy',
  43             'title': 'Sinkhole of bureaucracy',
  44         },
  45         'playlist': [{
  46             'md5': '7ccf53ea8cbb77de5f570242b3b21a59',
  47             'info_dict': {
  48                 'id': 'fc433c38-b146-11e3-b8b3-44b1d1cd4c1f',
  49                 'ext': 'mp4',
  50                 'title': 'Breaking Points: The Paper Mine',
  51                 'duration': 1290,
  52                 'description': 'Overly complicated paper pushing is nothing new to government bureaucracy. But the way federal retirement applications are filed may be the most outdated. David Fahrenthold explains.',
  53                 'timestamp': 1395440416,
  54                 'upload_date': '20140321',
  55                 'thumbnail': r're:https://[^\.]+.cloudfront\.net/PAPERMINESplash\.jpg',
  56             },
  57         }, {
  58             'md5': '7ccf53ea8cbb77de5f570242b3b21a59',
  59             'info_dict': {
  60                 'id': '41255e28-b14a-11e3-b8b3-44b1d1cd4c1f',
  61                 'ext': 'mp4',
  62                 'title': 'The town bureaucracy sustains',
  63                 'description': 'Underneath the friendly town of Boyers is a sea of government paperwork. In a disused limestone mine, hundreds of locals now track, file and process retirement applications for the federal government. We set out to find out what it\'s like to do paperwork 230 feet underground.',
  64                 'duration': 2220,
  65                 'timestamp': 1395441819,
  66                 'upload_date': '20140321',
  67                 'thumbnail': r're:https://[^\.]+.cloudfront\.net/BoyersSplash\.jpeg',
  68             },
  69         }],
  70     }, {
  71         'url': 'http://www.washingtonpost.com/blogs/wonkblog/wp/2014/12/31/one-airline-figured-out-how-to-make-sure-its-airplanes-never-disappear/',
  72         'info_dict': {
  73             'id': 'one-airline-figured-out-how-to-make-sure-its-airplanes-never-disappear',
  74             'title': 'One airline figured out how to make sure its airplanes never disappear',
  75         },
  76         'playlist': [{
  77             'md5': 'a7c1b5634ba5e57a6a82cdffa5b1e0d0',
  78             'info_dict': {
  79                 'id': '0e4bb54c-9065-11e4-a66f-0ca5037a597d',
  80                 'ext': 'mp4',
  81                 'description': 'Washington Post transportation reporter Ashley Halsey III explains why a plane\'s black box needs to be recovered from a crash site instead of having its information streamed in real time throughout the flight.',
  82                 'upload_date': '20141230',
  83                 'timestamp': 1419972442,
  84                 'title': 'Why black boxes don’t transmit data in real time',
  85             },
  86         }],
  87         'skip': 'Doesnt have a video anymore',
  88     }, {
  89         'url': 'https://www.washingtonpost.com/nation/2021/08/05/dixie-river-fire-california-climate/',
  90         'only_matching': True,
  91     }]
  92
  93     @classmethod
  94     def suitable(cls, url):
  95         return False if WashingtonPostIE.suitable(url) else super().suitable(url)
  96
  97     def _real_extract(self, url):
  98         page_id = self._match_id(url)
  99         webpage = self._download_webpage(url, page_id)
 100
 101         title = self._og_search_title(webpage)
 102
 103         uuids = re.findall(r'''(?x)
 104             (?:
 105                 <div\s+class="posttv-video-embed[^>]*?data-uuid=|
 106                 data-video-uuid=
 107             )"([^"]+)"''', webpage)
 108
 109         if not uuids:
 110             json_data = self._search_nextjs_data(webpage, page_id)
 111             for content_element in traverse_obj(json_data, ('props', 'pageProps', 'globalContent', 'content_elements')):
 112                 if content_element.get('type') == 'video':
 113                     uuids.append(content_element.get('_id'))
 114
 115         entries = [self.url_result(f'washingtonpost:{uuid}', 'WashingtonPost', uuid) for uuid in uuids]
 116
 117         return {
 118             '_type': 'playlist',
 119             'entries': entries,
 120             'id': page_id,
 121             'title': title,
 122         }